Research on classified real-time flood forecasting framework based on K-means cluster and rough set.

This research presents a new classified real-time flood forecasting framework. In this framework, historical floods are classified by a K-means cluster according to the spatial and temporal distribution of precipitation, the time variance of precipitation intensity and other hydrological factors. Based on the classified results, a rough set is used to extract the identification rules for real-time flood forecasting. Then, the parameters of different categories within the conceptual hydrological model are calibrated using a genetic algorithm. In real-time forecasting, the corresponding category of parameters is selected for flood forecasting according to the obtained flood information. This research tests the new classified framework on Guanyinge Reservoir and compares the framework with the traditional flood forecasting method. It finds that the performance of the new classified framework is significantly better in terms of accuracy. Furthermore, the framework can be considered in a catchment with fewer historical floods.

[1]  Jerzy W. Grzymala-Busse,et al.  Rough Sets , 1995, Commun. ACM.

[2]  You Jin.  New method for solving multi-objective problem based on genetic algorithm , 2003 .

[3]  Salvatore Greco,et al.  Discovering Reservoir Operating Rules by a Rough Set Approach , 2006 .

[4]  C. T. Wang,et al.  A representation of an instantaneous unit hydrograph from geomorphology , 1980 .

[5]  I. Rodríguez‐Iturbe,et al.  The geomorphologic structure of hydrologic response , 1979 .

[6]  Q. J. Wang.  The Genetic Algorithm and Its Application to Calibrating Conceptual Rainfall-Runoff Models , 1991 .

[7]  Ching-Lai Hwang,et al.  Multiple Attribute Decision Making: Methods and Applications - A State-of-the-Art Survey , 1981, Lecture Notes in Economics and Mathematical Systems.

[8]  Hou Zhao-cheng.  Cluster Validity Analysis for Flood Clustering , 2007 .

[9]  Wang Shun-jiu.  Projection Pursuit Model for Evaluating of Flood Events , 2002 .

[10]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[11]  Timothy K. Gates,et al.  Planning Reservoir Operations with Imprecise Objectives , 1997 .

[12]  Dragan Savic,et al.  Water Reservoir Control with Data Mining , 2003 .

[13]  D. Labat,et al.  Rainfall runoff relations for karstic springs. Part I: convolution and spectral analyses , 2000 .

[14]  Guangtao Fu,et al.  Classified real-time flood forecasting by coupling fuzzy clustering and neural network , 2010 .

[15]  S. Sorooshian,et al.  The Automatic Calibration of Conceptual Catchment Models Using Derivative‐Based Optimization Algorithms , 1985 .

[16]  John W. Labadie,et al.  Optimal Operation of Multireservoir Systems: State-of-the-Art Review , 2004 .

[17]  J. Seibert.  Multi-criteria calibration of a conceptual runoff model using a genetic algorithm , 2000 .

[18]  Robert LIN,et al.  NOTE ON FUZZY SETS , 2014 .

[19]  Andrzej Skowron,et al.  Rough sets and Boolean reasoning , 2007, Inf. Sci..

[20]  Ashu Jain,et al.  Integrated approach to model decomposed flow hydrograph using artificial neural network and conceptual techniques , 2006 .

[21]  Chuntian Cheng,et al.  Using genetic algorithm and TOPSIS for Xinanjiang model calibration with a single procedure , 2006 .

[22]  L. K. Sherman.  Streamflow from rainfall by the unit-graph method , 1932 .

[23]  Lucien Duckstein,et al.  Fuzzy Rule-Based Modeling of Reservoir Operation , 1996 .

[24]  Yang Guo-xing.  K-Means Clustering Analysis Based on Genetic Algorithm , 2008 .

[25]  H Rajaie,et al.  Runoff hydrograph simulation based on time variable isochrone technique , 2002 .

[26]  H. Madsen,et al.  Multiobjective calibration with Pareto preference ordering: An application to rainfall‐runoff model calibration , 2005 .